Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Bruhn, Andres"'
Attention-based motion aggregation concepts have recently shown their usefulness in optical flow estimation, in particular when it comes to handling occluded regions. However, due to their complexity, such concepts have been mainly restricted to coar
Externí odkaz:
http://arxiv.org/abs/2311.02661
Adversarial patches undermine the reliability of optical flow predictions when placed in arbitrary scene locations. Therefore, they pose a realistic threat to real-world motion detection and its downstream applications. Potential remedies are defense
Externí odkaz:
http://arxiv.org/abs/2310.17403
Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more realistic threat scenario. Hence
Externí odkaz:
http://arxiv.org/abs/2305.06716
While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence, we introduc
Externí odkaz:
http://arxiv.org/abs/2303.01943
In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this
Externí odkaz:
http://arxiv.org/abs/2210.16900
Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with adversarially opt
Externí odkaz:
http://arxiv.org/abs/2210.11242
Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work, we show tha
Externí odkaz:
http://arxiv.org/abs/2207.12163
Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically limited to only
Externí odkaz:
http://arxiv.org/abs/2207.05704
Autor:
Schmalfuss, Jenny, Scheurer, Erik, Zhao, Heng, Karantzas, Nikolaos, Bruhn, Andrés, Labate, Demetrio
Blind inpainting algorithms based on deep learning architectures have shown a remarkable performance in recent years, typically outperforming model-based methods both in terms of image quality and run time. However, neural network strategies typicall
Externí odkaz:
http://arxiv.org/abs/2205.06597
Recent optical flow methods are almost exclusively judged in terms of accuracy, while their robustness is often neglected. Although adversarial attacks offer a useful tool to perform such an analysis, current attacks on optical flow methods focus on
Externí odkaz:
http://arxiv.org/abs/2203.13214